Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6168 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3837. Min Range: -6.3837
Max Act: 6.3837. Min Act: -0.1700
Data Index: 784166 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3837. Min Range: -6.3837
Max Act: 6.0399. Min Act: -0.1700
Data Index: 8595489 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.9462. Min Act: -0.1700
Data Index: 7089098 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.9149. Min Act: -0.1700
Data Index: 3392767 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.8837. Min Act: -0.1700
Data Index: 805544 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.8524. Min Act: -0.1700
Data Index: 5344258 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.8524. Min Act: -0.1700
Data Index: 6884801 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.8524. Min Act: -0.1700
Data Index: 5922784 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.7899. Min Act: -0.1700
Data Index: 4578871 (Open Web Text)
Max Activating Token Index: 286
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.7587. Min Act: -0.1700
Data Index: 1639007 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.7587. Min Act: -0.1700
Data Index: 495533 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.7587. Min Act: -0.1700
Data Index: 1430798 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.7274. Min Act: -0.1700
Data Index: 6615416 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.7274. Min Act: -0.1700
Data Index: 3432782 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.6962. Min Act: -0.1700
Data Index: 6328889 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.6649. Min Act: -0.1700
Data Index: 840522 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.6649. Min Act: -0.1700
Data Index: 911750 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.6337. Min Act: -0.1700
Data Index: 5857826 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.6649. Min Act: -0.1700
Data Index: 1700261 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3837. Min Range: -6.3837
Max Act: 5.6649. Min Act: -0.1700
Data Index: 4804111 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19